© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45330
    Prev
    Next
    INDEX
    Explanations

    against

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Against
    -1.17
    against
    -1.14
     AGAINST
    -1.10
    Against
    -1.08
     against
    -1.05
    TagMode
    -1.01
    __":
    
    -1.00
    তথ্যসূত্র
    -0.98
     propOrder
    -0.96
    ')));
    -0.86
    POSITIVE LOGITS
     the
    1.18
     it
    0.99
     a
    0.89
     its
    0.77
     them
    0.75
     this
    0.75
     their
    0.73
     any
    0.72
     an
    0.69
    it
    0.68
    Activations Density 0.033%

    No Known Activations